[NeurIPS'2019] Shupeng Gui, Haotao Wang, Haichuan Yang, Chen Yu, Zhangyang Wang, Ji Liu, “Model Compression with Adversarial Robustness: A Unified Optimization Framework”

✭ 41

python pruning quantization robustness model-compression unified-optimization-framework

Stochastic-Quantization

Training Low-bits DNNs with Stochastic Quantization

✭ 70

Jupyter Notebook C++python Cuda CMake Protocol Buffer deep-neural-networks caffe imagenet cifar quantization

neural-compressor

Intel® Neural Compressor (formerly known as Intel® Low Precision Optimization Tool), targeting to provide unified APIs for network compression technologies, such as low precision quantization, sparsity, pruning, knowledge distillation, across different deep learning frameworks to pursue optimal inference performance.

✭ 666

python javascript typescript HTML Jupyter Notebook SCSS sparsity deep-learning pruning quantization knowledge-distillation auto-tuning low-precision quantization-aware-training post-training-quantization

local-search-quantization

State-of-the-art method for large-scale ANN search as of Oct 2016. Presented at ECCV 16.

✭ 70

julia Cuda C++matlab computer-vision gpu cuda quantization eccv-16 multi-codebook

mmn

Moore Machine Networks (MMN): Learning Finite-State Representations of Recurrent Policy Networks

✭ 39

python shell deep-reinforcement-learning pytorch recurrent-neural-networks finite-state-machine tomita atari quantization bottleneck interpretability moore-machine explainable-artificial-intelligence

torch-model-compression

针对pytorch模型的自动化模型结构分析和修改工具集，包含自动分析模型结构的模型压缩算法库

✭ 126

python pytorch pruning quantization tensorrt model-compression qat onnx reparameterization tensorrt-conversion quantization-aware-training acnet

Neural-Network-Compression

Paper list for neural network compression techniques

✭ 31

deep-learning neural-network quantization neural-network-compression model-compression-papers

sparsezoo

Neural network model repository for highly sparse and sparse-quantized models with matching sparsification recipes

BitPack

BitPack is a practical tool to efficiently save ultra-low precision/mixed-precision quantized models.

✭ 36

python memory pytorch quantization model-compression mixed-precision quantized-neural-networks

deepvac

PyTorch Project Specification.

✭ 507

python amp pytorch tensorboard quantization ddp tensorrt coreml ncnn onnx torchscript deepvac

fastT5

⚡ boost inference speed of T5 models by 5x & reduce the model size by 3x.

✭ 421

python nlp fast translation deep-learning inference pytorch transformer question-answering quantization onnx t5 onnxruntime fastt5 quantized-onnx-models inference-speed

ZAQ-code

CVPR 2021 : Zero-shot Adversarial Quantization (ZAQ)

✭ 59

python quantization zero-shot model-compression distillation

MQBench Quantize

QAT(quantize aware training) for classification with MQBench

✭ 29

python lsq resnet pact quantization qat dsq efficientnetb0 mqbench regnetx

TF2DeepFloorplan

TF2 Deep FloorPlan Recognition using a Multi-task Network with Room-boundary-Guided Attention. Enable tensorboard, quantization, flask, tflite, docker, github actions and google colab.

61-81 of 81 quantization projects

‹